Noometry

OpenAI, proprietary

GPT-6 Luna

GPT-6 Luna by OpenAI ranks 36th of 354 ranked models on the Noometry Index as of October 2026, with a score of 53.3. Its strongest category is math, where it ranks 15th. API pricing starts at $0.10 per million input tokens and $0.50 per million output tokens, with a 1.05M-token context window.

Last verified

Noometry rank
#36 of 354
Index score
53.3
Evidence
Confirmed 42 results
Provider
OpenAI
Released
September 22, 2026
Weights
Proprietary
Reasoning
Yes
Context window
1.05M
Max output
128K
Input price
$0.10 / M
Output price
$0.50 / M
Blended price
$0.20 / M
Output speed
Not measured
Value
#26 of 219
Knowledge cutoff
May 2026
Input
text, image, pdf

Category scores

Each category score combines every public result we have in that category.

  1. Coding 55.5
  2. Agentic & Tool Use 33.3
  3. Reasoning 48.2
  4. Math 76.1
  5. Knowledge 57.0
  6. Multimodal 42.4
  7. Multilingual 50.5
  8. Instruction Following 74.3
  9. Long Context 43.0
  10. Writing & Preference 58.3
CategoryScoreRankResults
Coding55.5#255
Agentic & Tool Use33.3#542
Reasoning48.2#419
Math76.1#155
Knowledge57.0#413
Multimodal42.4#303
Multilingual50.5#1171
Instruction Following74.3#991
Long Context43.0#1111
Writing & Preference58.3#1193

Strengths and weaknesses

Categories where GPT-6 Luna places highest and lowest among the models ranked in each, with its score against that category's median.

Strongest categories

CategoryScorevs medianRank
Math76.1+39.5#15 of 327, top 5%
Coding55.5+16.8#25 of 340, top 8%
Reasoning48.2+24.6#41 of 350, top 12%

Weakest categories

CategoryScorevs medianRank
Multilingual50.5+3.1#117 of 297, top 40%
Writing & Preference58.3+4.5#119 of 312, top 39%
Long Context43.0+2.1#111 of 296, top 38%

Closest competitors

The models ranked just above and below GPT-6 Luna. When scores are this close, price and speed are often the better way to choose.

ModelRankScoreBlended $/MSpeed
Gemini 3.5 Flash#3254.2$3.38—Compare
Gemini 3.6 Flash#3354.1$1.50—Compare
GPT-5.2#3454.1$4.8115Compare
DeepSeek V4 Flash#3553.6$0.266Compare
Grok 4.7#3753.1$3—Compare
DeepSeek V4.1 Flash#3852.8$0.26—Compare
GPT-5.2 Pro#3952.3$57.75—Compare
Gemini 3 Flash Preview#4052.3$1.13—Compare

Sponsored placements are available on pages like this one. Advertise on Noometry

Benchmark results

Every published result we track, with its source. Bold rows are the ones used for ranking; where several exist we prefer independent runs over self-reported numbers.

Coding

BenchmarkScorePositionSettingSourceDate
DeepSWE59.3%highModel card (self-reported)2026-09-22
DeepSWE2.4%lowModel card (self-reported)2026-09-22
DeepSWE66.6%#14 of 29, top 49%maxModel card (self-reported)2026-09-22
DeepSWE44.5%mediumModel card (self-reported)2026-09-22
DeepSWE61.3%xhighModel card (self-reported)2026-09-22
FrontierCode42.4%#18 of 37, top 49%maxEpoch AI
FrontierCode37.3%highModel card (self-reported)2026-09-22
FrontierCode25.7%lowModel card (self-reported)2026-09-22
FrontierCode42.4%maxModel card (self-reported)2026-09-22
FrontierCode35.5%mediumModel card (self-reported)2026-09-22
FrontierCode37.1%xhighModel card (self-reported)2026-09-22
LMArena WebDev1581#29 of 113, top 26%LMArena2026-10-08
SciCode50.3%highEpoch AI
SciCode46.9%lowEpoch AI
SciCode54.6%#26 of 121, top 22%maxEpoch AI
SciCode50.9%mediumEpoch AI
SciCode43.1%noneEpoch AI
SciCode51.7%xhighEpoch AI
LMArena Coding1439#98 of 294, top 34%LMArena2026-10-08
ALE-Bench1,577#14 of 105, top 14%xhighEpoch AI

Agentic & Tool Use

BenchmarkScorePositionSettingSourceDate
APEX-Agents44.3%#33 of 49, top 68%maxEpoch AI
GDP.pdf23%#16 of 36, top 45%maxEpoch AI

Reasoning

BenchmarkScorePositionSettingSourceDate
ARC-AGI-231.4%highEpoch AI
ARC-AGI-24.6%lowEpoch AI
ARC-AGI-259.3%#31 of 83, top 38%maxEpoch AI
ARC-AGI-218.1%mediumEpoch AI
ARC-AGI-20%noneEpoch AI
ARC-AGI-241.9%xhighEpoch AI
NYT Connections (extended)68.7%#51 of 91, top 57%high reasoningLech Mazur benchmarks
ARC-AGI-170.3%highEpoch AI
ARC-AGI-137.7%lowEpoch AI
ARC-AGI-186.7%#33 of 83, top 40%maxEpoch AI
ARC-AGI-161%mediumEpoch AI
ARC-AGI-18.8%noneEpoch AI
ARC-AGI-173%xhighEpoch AI
CritPt15.4%highEpoch AI
CritPt2.6%lowEpoch AI
CritPt19.4%#26 of 134, top 20%maxEpoch AI
CritPt10.6%mediumEpoch AI
CritPt1.1%noneEpoch AI
CritPt17.4%xhighEpoch AI
Chess Puzzles31%#34 of 129, top 27%maxEpoch AI2026-09-22
LMArena Hard Prompts1411#116 of 297, top 40%LMArena2026-10-08
Mystery Game Puzzles7%#67 of 74, top 91%maxEpoch AI2026-09-22
DTBench90.1%#38 of 151, top 26%maxEpoch AI
LMCA44.5%#35 of 125, top 29%maxEpoch AI
Epoch Capabilities Index156.28#24 of 213, top 12%Epoch AI2026-09-22

Math

BenchmarkScorePositionSettingSourceDate
FrontierMath (Tiers 1-3)78.9%#16 of 81, top 20%maxEpoch AI2026-09-22
FrontierMath Tier 456.1%#17 of 63, top 27%maxEpoch AI2026-09-22
OTIS Mock AIME 2024-202598.9%#18 of 173, top 11%maxEpoch AI2026-09-22
ProofBench64%#17 of 77, top 23%Epoch AI
LMArena Math1416#108 of 285, top 38%LMArena2026-10-08

Knowledge

BenchmarkScorePositionSettingSourceDate
GPQA Diamond90.5%#36 of 186, top 20%maxEpoch AI2026-09-22
SimpleQA Verified41.4%#39 of 77, top 51%maxEpoch AI2026-09-22
LMArena Expert1444#76 of 273, top 28%LMArena2026-10-08

Multimodal

BenchmarkScorePositionSettingSourceDate
LMArena Vision1217#72 of 122, top 60%LMArena2026-10-09
Blueprint-Bench 231.2%#14 of 31, top 46%Epoch AI
Furniture Assembly44.2%#12 of 31, top 39%maxEpoch AI2026-09-28

Multilingual

BenchmarkScorePositionSettingSourceDate
LMArena Non-English1386#117 of 297, top 40%LMArena2026-10-08
LMArena Chinese1433#115 of 285, top 41%LMArena2026-10-08
LMArena French1420#100 of 223, top 45%LMArena2026-10-08
LMArena German1369#117 of 231, top 51%LMArena2026-10-08
LMArena Japanese1369#87 of 211, top 42%LMArena2026-10-08
LMArena Korean1360#93 of 213, top 44%LMArena2026-10-08
LMArena Russian1394#113 of 283, top 40%LMArena2026-10-08
LMArena Spanish1393#117 of 226, top 52%LMArena2026-10-08

Instruction Following

BenchmarkScorePositionSettingSourceDate
LMArena Instruction Following1409#88 of 298, top 30%LMArena2026-10-08

Long Context

BenchmarkScorePositionSettingSourceDate
LMArena Longer Query1409#108 of 291, top 38%LMArena2026-10-08

Writing & Preference

BenchmarkScorePositionSettingSourceDate
LMArena Text1391#128 of 297, top 44%LMArena2026-10-08
LMArena Creative Writing1363#118 of 295, top 40%LMArena2026-10-08
LMArena Multi-Turn1396#124 of 295, top 43%LMArena2026-10-08

API pricing by provider

RouteInput $/MOutput $/MCached input $/MChecked
azure$0.10$0.50$0.012026-10-10
bedrock$0.10$0.50$0.012026-10-10
openai$0.10$0.50$0.012026-10-10
openrouter$0.10$0.50$0.012026-10-10

All OpenAI API prices → Estimate your cost →

Compare GPT-6 Luna

Other OpenAI models

Frequently asked questions

How good is GPT-6 Luna?

GPT-6 Luna by OpenAI ranks 36th of 354 ranked models on the Noometry Index as of October 2026, with a score of 53.3. Its strongest category is math, where it ranks 15th. API pricing starts at $0.10 per million input tokens and $0.50 per million output tokens, with a 1.05M-token context window.

How much does GPT-6 Luna cost?

GPT-6 Luna costs $0.10 per million input tokens and $0.50 per million output tokens on OpenAI's own API, with cached input at $0.01.

What is GPT-6 Luna's context window?

GPT-6 Luna accepts up to 1.05M tokens of input and can write up to 128K tokens in one response.

Is GPT-6 Luna open source?

No. GPT-6 Luna is proprietary and available only through OpenAI's API and partner platforms.

What are GPT-6 Luna's strengths and weaknesses?

Relative to other ranked models, GPT-6 Luna places best in math, coding, reasoning and lowest in multilingual, writing & preference, long context.

What is GPT-6 Luna best at?

Its best category is math, where it ranks 15th on Noometry.